Transform- and multi-domain deep learning for single-frame rapid autofocusing in whole slide imaging
Transform- and multi-domain deep learning for single-frame rapid autofocusing in whole slide imaging
复制标题
DOI：
10.1364/boe.9.001601
复制
发表时间：
2018-04-01
影响因子：
3.4
通讯作者：
Zheng, Guoan
中科院分区：
文献类型：
--
作者：
Jiang, Shaowei;Liao, Jun;Zheng, Guoan
一种完整的滑动成像（WSI）系统最近在美国被批准用于初级诊断。WSI的图像质量和系统吞吐量在很大程度上取决于自动对焦过程。传统的方法沿着光轴获取多幅图像，并最大化自动对焦的优点。在这里，我们探索使用深度卷积神经网络（cnn）来预测无需轴向扫描的获取图像的焦点位置。研究了非相干科勒照明、双平面波部分相干照明和单平面波照明三种照明条件下的自动对焦性能。我们获得了大约13万张不同离焦距离的图像作为训练数据集。不同的离焦距离导致捕获图像的空间特征不同。然而，单纯依靠空间信息会导致自动对焦过程的性能相对较差。最好从图像的变换域中提取离焦特征。对于非相干照明，傅里叶截止频率与离焦距离直接相关。同样，自相关峰与两平面波照明的离焦距离直接相关。在我们的实现中，我们使用空间图像、傅里叶谱、空间图像的自相关及其组合作为cnn的输入。结果表明，变换域的信息可以提高自动聚焦过程的性能和鲁棒性。由此产生的对焦误差约为0.5 μ m，在0.8 μ m的景深范围内。所报道的方法对传统WSI系统的硬件修改很少，并且可以在没有焦点地图测量的情况下实时捕获图像。它可以在WSI和延时显微镜中找到应用。转换和多域方法也可能为开发与显微镜相关的深度学习网络提供新的见解。我们已经为广泛的研究社区开放了我们的训练和测试数据集（类似于12 GB）。(c)根据OSA开放获取出版协议的条款，2018年美国光学学会
A whole slide imaging (WSI) system has recently been approved for primary diagnostic use in the US. The image quality and system throughput of WSI is largely determined by the autofocusing process. Traditional approaches acquire multiple images along the optical axis and maximize a figure of merit for autofocusing. Here we explore the use of deep convolution neural networks (CNNs) to predict the focal position of the acquired image without axial scanning. We investigate the autofocusing performance with three illumination settings: incoherent Kohler illumination, partially coherent illumination with two plane waves, and one-plane-wave illumination. We acquire similar to 130,000 images with different defocus distances as the training data set. Different defocus distances lead to different spatial features of the captured images. However, solely relying on the spatial information leads to a relatively bad performance of the autofocusing process. It is better to extract defocus features from transform domains of the acquired image. For incoherent illumination, the Fourier cutoff frequency is directly related to the defocus distance. Similarly, autocorrelation peaks are directly related to the defocus distance for two-plane-wave illumination. In our implementation, we use the spatial image, the Fourier spectrum, the autocorrelation of the spatial image, and combinations thereof as the inputs for the CNNs. We show that the information from the transform domains can improve the performance and robustness of the autofocusing process. The resulting focusing error is similar to 0.5 mu m, which is within the 0.8-mu m depth-of-field range. The reported approach requires little hardware modification for conventional WSI systems and the images can be captured on the fly without focus map surveying. It may find applications in WSI and time-lapse microscopy. The transform-and multi-domain approaches may also provide new insights for developing microscopy-related deep-learning networks. We have made our training and testing data set (similar to 12 GB) opensource for the broad research community. (c) 2018 Optical Society of America under the terms of the OSA Open Access Publishing Agreement